Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates in the month of November

    oai_token-act-pair · gpt-3.5-turbo

    dates in November

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.96
    ldon
    -0.80
    pires
    -0.79
    king
    -0.76
    gypt
    -0.74
     attendant
    -0.74
    SPA
    -0.73
    ensed
    -0.72
    Reviewer
    -0.71
    cher
    -0.71
    POSITIVE LOGITS
    е
    0.85
    flower
    0.83
     2012
    0.82
     1942
    0.80
     2014
    0.80
     2016
    0.79
     2015
    0.78
     2017
    0.76
     2013
    0.76
     2010
    0.76
    Act Density 0.013%

    No Known Activations